Chai Discovery Inks Agreement with Pfizer to Accelerate AI Drug Discovery
Advertisement
The latest model builds on the 2025 model release Chai-2, which the San Francisco startup described as the first zero-shot antibody design platform
San Francisco-based Chai Discovery has announced a licensing agreement with Pfizer aimed at deploying Chai's AI platform across Pfizer’s drug discovery operations.
Under the agreement, Pfizer will gain early access to Chai-3, the company's latest AI model, as well as a custom model developed using Pfizer's proprietary data and tailored to its research workflows.
The collaboration is intended to support Pfizer's efforts to accelerate drug discovery and expand its biologics research capabilities.
Chai Discovery builds generative AI software that can predict and reprogram the interactions between molecules, enabling scientists to design biomolecules with specific functional properties.
Its platforms are aimed at streamlining the traditionally time-consuming early stages of drug discovery by enabling the design of biomolecules from scratch, targeting complex biological processes, and shortening discovery cycles.
As per the startup, the new model is a major improvement in its AI antibody design.
It reported a double success rate as compared to its predecessor by reducing the failure rate while still producing candidates that meet therapeutic standards.
The model is designed to improve binding in therapeutic settings, help engineer multi-specific molecules, and work better against targets that traditional drug discovery methods have found difficult.
Commenting on the latest partnership, Joshua Meier, co-founder of Chai Discovery, said, “Our work with Pfizer is about putting Chai’s software directly into the hands of one of the world’s leading drug discovery organizations. By combining Chai’s frontier AI platform with Pfizer’s scientific depth, data, and discovery capabilities, we see an opportunity to expand and accelerate what is possible in biologics discovery and help Pfizer pursue targets that traditional methods have struggled to reach.”
The latest model builds on the 2025 model release Chai-2, which the San Francisco startup described as the first zero-shot antibody design platform to achieve double-digit experimental hit rates and design molecules with drug-like properties.
As per the startup, the platform delivered a 100-fold improvement over previous computational approaches, enabling discovery processes to be completed in weeks that previously required months.
Earlier this year, Chai Discovery announced a collaboration with Eli Lilly and Company to design novel biologic therapeutics across multiple discovery targets.
As part of the agreement, the organizations will also develop a purpose-built AI model that will be trained exclusively on Lilly’s proprietary data and tailored to the pharmaceutical company’s internal discovery workflows.
Stay tuned for more such updates on Digital Health News
